This repository is the code implementation for ECCV 2022 paper supplementary: "DeepShadow: Neural Shape from Shadow".

The overview of our shadow and light extraction architecture is shown below:

• torch > 1.8
• opencv-python > 4.1
• numpy
• kornia > 0.6
• matplotlib
• einops > 0.3.1
• python

Our code was tested using Python 3.7/3.8 under Ubuntu 18.04, with GPU and/or CPU.

skip this if you don't want to train the model

Download Blobby and Sculptures dataset by Chen et al. (taken from here - https://github.com/guanyingc/SDPS-Net) Torch data loading code also taken from here.

Download our PhotometricStereo Shadow data - (coming soon!)

1. Clone the repo -

git clone https://github.com/asafkar/ps_shadow_extract.git
cd ps_shadow_extract/

2. Download the model checkpoint

# get the checkpoint from the git lfs
git lfs install
git lfs fetch

3. Install requirements

pip install -r requirements.txt

4. Use the pretrained model to estimate shadows and lights directions

refer to run_model_example.ipynb

1. Download and unzip the data, place all 3 datasets in the same folder. Indicate the folder when training by using arg --base_dir

2. Train the model

CUDA_VISIBLE_DEVICES=<gpus> python -m torch.distributed.run --nproc_per_node=<num_gpus> train.py --base_dir=<dir>

If you use the model or dataset in your own research, please cite:

@inproceedings{karnieli2022deepshadow,	
		title={DeepShadow: Neural shape from shadows},
		author={Asaf Karnieli, Ohad Fried, Yacov Hel-Or},	
		year={2022},	
		booktitle={ECCV},
}